Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0688. Min Act: -0.0001

Data Index: 838041 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0088. Min Act: -0.0001

Data Index: 208522 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.0688. Min Range: -1.0688

Max Act: 1.0025. Min Act: -0.0001

Data Index: 1332726 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9744. Min Act: -0.0001

Data Index: 775171 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9135. Min Act: -0.0001

Data Index: 860316 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9239. Min Act: -0.0001

Data Index: 249623 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9565. Min Act: -0.0001

Data Index: 1039296 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9458. Min Act: -0.0001

Data Index: 426073 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8872. Min Act: -0.0001

Data Index: 823784 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.9203. Min Act: -0.0001

Data Index: 639784 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8884. Min Act: -0.0001

Data Index: 656060 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8546. Min Act: -0.0001

Data Index: 811678 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8726. Min Act: -0.0001

Data Index: 631849 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8655. Min Act: -0.0001

Data Index: 60039 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8582. Min Act: -0.0001

Data Index: 368106 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8615. Min Act: -0.0001

Data Index: 530440 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8606. Min Act: -0.0001

Data Index: 986401 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8380. Min Act: -0.0001

Data Index: 203298 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8515. Min Act: -0.0001

Data Index: 1320058 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8542. Min Act: -0.0001

Data Index: 1334819 (C4 (Web Text))

Max Activating Token Index: 447